What they do
open source approval layer for AI agent actions
How close to us
3, close
Central rules and approvals across agents; governs rather than does the work, so close to W2 ground.
Wedges
- W2 Seeing whether your AI agents actually produce adjacent
L1 Company brain (knows the organisation) 1, light
L2 Agent team (runs agents, tools, approvals) 2, clear
L3 Does and learns (finishes, checks, measures, updates the brain) 0, none
Who buys
- Firm size
- not known
- Buyer type
- developer
- Role
- engineering lead
- UK
- not known
Their own description (from YC)
withHuman is an open source approval layer for AI Agents.
When you want agents to take consequential actions like refund a customer, that's when withHuman is useful.
It is a centralized point where you can encode rules like "refunds < $10 can be done automatically, anything more than that, send it to the on-call from customer support". You write your rules once and connect all of your agents, no changes needed, its transparent to the agent.
Full teardown
No full teardown yet. On the deep list.
Technical detail
- Slug
- withhuman
- Lens hash
- 179096c479
- Pass
- screen
- Stale
- no